Moment estimates implied by modified log-Sobolev inequalities
Rados{\l}aw Adamczak, Witold Bednorz, Pawe{\l} Wolff

TL;DR
This paper explores a broad class of modified log-Sobolev inequalities, establishing their implications for moment estimates, concentration inequalities, and non-Euclidean gradient norms, extending classical results.
Contribution
It generalizes modified log-Sobolev inequalities and derives new $L^p$-Sobolev inequalities with non-Euclidean norms, leading to enhanced concentration results.
Findings
Modified inequalities imply $L^p$-Sobolev inequalities with non-Euclidean norms
Derived concentration inequalities for smooth functions and set enlargements
Established a two-level concentration for functions with bounded Hessian
Abstract
We study a class of logarithmic Sobolev inequalities with a general form of the energy functional. The class generalizes various examples of modified logarithmic Sobolev inequalities considered previously in the literature. Refining a method of Aida and Stroock for the classical logarithmic Sobolev inequality, we prove that if a measure on satisfies a modified logarithmic Sobolev inequality then it satisfies a family of -Sobolev-type inequalities with non-Euclidean norms of gradients (and dimension-independent constants). The latter are shown to yield various concentration-type estimates for deviations of smooth (not necessarily Lipschitz) functions and measures of enlargements of sets corresponding to non-Euclidean norms. We also prove a two-level concentration result for functions of bounded Hessian and measures satisfying the classical logarithmic Sobolev…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
